calibre/recipes/gkt.recipe
2021-01-04 13:16:28 +05:30

45 lines
1.5 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
class GKT(BasicNewsRecipe):
title = u'General Knowledge Today'
language = 'en_IN'
__author__ = 'Kovid Goyal'
oldest_article = 7 # days
max_articles_per_feed = 20
no_stylesheets = True
no_javascript = True
auto_cleanup = True
def parse_gkt_section(self, url, ignore_error=False):
try:
root = self.index_to_soup(url, as_tree=True)
except Exception:
if ignore_error:
return
raise
for a in root.xpath('//div[@class="posts-listing"]/h1/a[@href]'):
title = self.tag_to_string(a).strip()
url = a.get('href')
if title and url:
self.log('\tFound article:', title, 'at', url)
yield {'title': title, 'url': url}
def parse_index(self):
url = 'http://www.gktoday.in/'
root = self.index_to_soup(url, as_tree=True)
ans = []
h3 = root.xpath('//h3[@class="widget-title"]')[1]
for a in h3.getparent().xpath('descendant::li/a[@href]'):
category = self.tag_to_string(a).strip()
if 'PDF' in category or not category:
continue
url = a.get('href')
self.log('Found section:', category, 'at', url)
articles = list(self.parse_gkt_section(url)) + \
list(self.parse_gkt_section(url + '/page/2', ignore_error=True))
if articles:
ans.append((category, articles))
return ans